Accelerating materials design with high-throughput experiments and data science

Advances in machine learning and computational modeling have revolutionized materials design by enabling researchers to predict, optimize, and discover advanced materials far more efficiently than what is achieved via traditional experimental methods alone.

Professor Toshiaki Taniike from Japan Advanced Institute of Science and Technology (JAIST), who leads the Laboratory on Materials Informatics, is at the forefront of this new era in materials design. His laboratory focuses on accelerating the discovery and development of advanced materials by integrating high-throughput experiments, data science, and computer simulations. These approaches are applied to a wide range of materials, including catalysts, polymers, nanocomposites, and nanomaterials such as metal-organic frameworks (MOFs) and graphene.

From a young age Taniike had a clear ambition – he dreamt of becoming a scientist. Early in his academic journey, he directed his effort toward inventing new chemical reactions. Today, as head of the Laboratory on Materials Informatics at JAIST, Professor Taniike continues to pursue that dream. From designing and discovering advanced materials, he and his team are working on all that it takes to solve real-world problems in smarter, more efficient ways.

“I studied chemical engineering to learn the basics of process design. But I realized I needed a deeper understanding of how chemical reactions actually work. That led me to quantum physics and simulations. However, simulations cannot fully capture the complexity of real reactions, so I returned to experiments, focusing on catalysis, because catalysts drive about 80% of chemical processes,” says Prof. Taniike, sharing how he voyaged through this field. Over time, he learned that discovery often comes through trial and error, so now, he combines high-throughput experiments with data science and machine learning to make this process faster and smarter.

Breaking from tradition: A smarter way to discover materials

Traditionally, discovering new materials or chemical reactions was mainly pursued as a trial-and-error experiment. Researchers would use what they already knew to take a calculated guess about which features or descriptors matter most when designing a new material. For example, they might think that surface area or crystal structure will affect catalyst performance and then test that idea. This worked well for improving things we already understand, but its utility is limited for discovering truly new reactions or materials because you cannot guess what you do not know.

What Prof. Taniike’s lab does differently is to combine high-throughput experimentation with machine learning techniques like automatic feature engineering. Instead of relying on human intuition to choose descriptors, they let the machine automatically generate and test thousands or even millions of possible descriptors to find the ones that really matter. They then run experiments in parallel to test these ideas, which makes the process 10 to 1000 times faster than doing it manually. Moving beyond the traditional trial-and-error approach, this lets them discover reactions or materials that were impossible to find before.

One such example is the oxidative coupling of methane (OCM), which is sometimes called a “dream reaction.” It aims to convert methane — the most abundant hydrocarbon feedstock — directly into ethylene, which is extremely valuable for producing plastics and chemicals. This is very challenging because methane is such a stable molecule. Usually, when you try to activate it, it just burns completely to CO₂. The idea behind OCM is to carefully control this process so that instead of complete combustion, you stop the reaction at the ethylene stage. This could help reduce CO₂ emissions from the chemical sector. Published in ACS Catalysis in 2020, Prof. Taniike’s study presents a high-throughput system for the OCM, generating a large, consistent dataset that enables automated performance evaluation, insightful data visualization, and accurate C₂ yield prediction through nonlinear machine learning.

Another study published in Communications Chemistry presents a combination of automatic feature engineering with the above high-throughput system, to streamline the discovery of high-performing catalysts for the OCM through automated descriptor design.

The team is also moving toward discovering entirely new kinds of reactions that could someday transform fields like energy, carbon recycling, or sustainable chemical manufacturing.

‘Sen Tan’ (cutting-edge) aspect of Prof. Taniike’s research

 Prof. Taniike believes that the way he and his team combines high-throughput experimentation with automatic feature engineering and machine learning to discover catalysts and reactions at a scale and speed that were not possible before, sets his research apart. For example, instead of just optimizing known reactions, we can now explore totally unknown chemical spaces and test thousands of hypotheses automatically. This shift to a more strategic and data-driven approach is truly pushing the boundaries of what is possible in chemical discovery.

From data to discovery: What comes next?

Prof. Taniike’s research goes beyond just materials design – it also deals with creating new methods that can transform how we tackle big challenges in other fields like energy, medicine, and even other industries. For example, data-driven approaches can accelerate the development of carbon-neutral processes to help reduce CO₂ emissions, such as producing ammonia more efficiently or generating hydrogen from renewable energy sources. At the same time, these methods can also be applied in any field that relies on large amounts of experimental data. In fact, his lab’s expertise in designing highly efficient, automated experiments has attracted interest from companies in diverse sectors. Some companies have even sought help for designing their own experimental setups to save time and resources including unexpected areas like soap manufacturing. This kind of automation is especially important in countries like Japan which are facing labor shortages due to a declining population.

By doing all of this, Prof. Taniike’s goal is to help solve big global challenges like achieving a carbon-neutral society. As he explains, “Many of today’s processes, especially in energy and chemicals, create huge CO₂ emissions because the available reactions and catalysts are limited. My hope is that our work in discovering unknown reactions will help solve some of the big bottlenecks that stand in the way of a more sustainable society.”

Inspiring the future

Prof. Taniike believes in always taking up challenges to do something new. While established ways of working can offer comfort, breakthroughs often come when one questions old assumptions or changes their environment. In his own career, Prof. Taniike changed fields multiple times — from chemical engineering to quantum physics to data-driven research. Drawing parallels from his own life experience, he says, “While it can be difficult, but if you stick to your vision and keep pushing boundaries, you will find original ideas and make real contributions.”

In his lab, he believes in providing an interdisciplinary and international environment for researchers, that combines high-throughput experimentation, data science, and computational chemistry, so that they can learn cutting-edge techniques that are not common in traditional labs. Because thousands of reactions and catalysts are conducted at the same time, lab designs and custom instruments must be tailored to the research needs, making it imperative to collaborate with industrial partners, work with companies to manufacture the instruments, test prototypes, and refine them to make experiments faster, cheaper, and more efficient. Students can thus get hands-on experience not only using advanced equipment but also contributing to this development cycle with industry partners. This gives them practical skills that are valuable in both academia and industry.

How JAIST propels the culture of forward-thinking research

For Prof. Taniike, JAIST is unique because it is a graduate-only university — they do not offer undergraduate programs — so professors can focus more fully on advanced research and mentoring. The environment is highly interdisciplinary, bringing together chemistry, materials science, computer science, and engineering under one roof. This collaborative atmosphere makes it much easier to tackle complex, real-world challenges that do not fit neatly into one field. Plus, JAIST is very international, which is essential for driving fresh ideas and innovation.

***

About Japan Advanced Institute of Science and Technology, Japan

Founded in 1990 in Ishikawa prefecture, the Japan Advanced Institute of Science and Technology (JAIST) was the first independent national graduate university that has its own campus in Japan to carry out research-based graduate education in advanced science and technology. The term “Advanced” in JAIST’s name reflects the Japanese term “Sen Tan,” meaning “cutting-edge,” representing the university’s focus on being at the forefront of innovative research and education. Now, after 30 years of steady progress, JAIST has become one of Japan’s top-ranking universities. JAIST aims to foster capable leaders through its advanced education and research curricula. About 40% of JAIST’s alumni are international students. The university has a unique style of graduate education to ensure that students have a thorough foundation to build cutting-edge research and technology in the future. JAIST also works closely with both local and overseas academic and industrial communities, promoting industry–academia collaborative research.

Website: https://www.jaist.ac.jp/english/